config.json

{
  "activation_function": "gelu_new",
  "architectures": [
    "GPTNeoForCausalLM"
  ],
  "attention_dropout": 0,
  "attention_layers": [
    "global",
    "global",
    "global",
    "global",
    "global",
    "global",
    "global",
    "global",
    "global",
    "global",
    "global",
    "global"
  ],
  "attention_types": [
    [
      [
        "global"
      ],
      12
    ]
  ],
  "embed_dropout": 0,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": null,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 2048,
  "eos_token_id" : 0,
  "bos_token_id" : 0,
  "pad_token_id" : 1,
  "model_type": "gpt_neo",
  "num_heads": 12,
  "num_layers": 12,
  "resid_dropout": 0,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "torch_dtype": "float32",
  "transformers_version": "4.20.0",
  "use_cache": true,
  "vocab_size": 63999,
  "window_size": 256,
  "task_specific_params": {    
      "text-generation": 
      {
      "do_sample": false,
      "max_length": 300,
      "num_beams": 5,
      "top_p": 0.95,
      "repetition_penalty": 3.0, 
      "no_repeat_ngram_size": 3  
      }   
      }
}